Time Series Forecasting Based on ARIMA and LSTM

DOI

10.2991/aebmr.k.220603.195How to use a DOI?

Keywords

Time series forecasting; Stock price forecasting; Deep Learning; ARIMA; LSTM

Abstract

With the increasing demand for designing a future strategy to minimize risk and make a benefit. The time series analysis becomes an essential tool in social science, engineering, and finance. Therefore, investors and researchers endeavor to investigate kinds of models to improve the accuracy of the forecasting result. Originally, Autoregression (AR) and Moving average (MA) model was developed to forecast next period data. Moreover, ARIMA was built to solve the non-stationarity of data. Besides, ARCH and GARCH were built to capture the volatility of data. Later, the neural network model in deep learning gets its popularity with higher accuracy for prediction. ANN model and LSTM model are widely used in time series analysis for the different research areas. By evaluating the performance between the traditional ARIMA model and burgeoning LSTM model on stock price prediction, the paper could guide investors to manage their assets with time series forecasting tools.

Copyright

© 2022 The Authors. Published by Atlantis Press International B.V.

Open Access

This is an open access article distributed under the CC BY-NC 4.0 license.

Download article (PDF)

TY  - CONF
AU  - Peiqi Liu
PY  - 2022
DA  - 2022/07/01
TI  - Time Series Forecasting Based on ARIMA and LSTM
BT  - Proceedings of the 2022 2nd International Conference on Enterprise Management and Economic Development (ICEMED 2022)
PB  - Atlantis Press
SP  - 1203
EP  - 1208
SN  - 2352-5428
UR  - https://doi.org/10.2991/aebmr.k.220603.195
DO  - 10.2991/aebmr.k.220603.195
ID  - Liu2022
ER  -